Update app.py

app.py

@@ -265,7 +265,7 @@ from sklearn.metrics.pairwise import cosine_similarity
 from sklearn.feature_extraction.text import TfidfVectorizer
 from datetime import datetime
 
-# Load the legislative dataset
+# Load dataset
 @st.cache_data
 def load_data():
     df = pd.read_csv("Illinois_Entire_Data_Insights_Final_v2.csv")
@@ -276,25 +276,25 @@ def load_data():
     df["summary_insight"] = df["llama_trend_summary"] + "\n" + df["llama_insight"]
     return df
 
-# Load embedding and summarization models
+# Load models
 @st.cache_resource
 def load_models():
     embed_model = SentenceTransformer('all-MiniLM-L6-v2')
     summarizer = pipeline("summarization", model="t5-small", tokenizer="t5-small")
     return embed_model, summarizer
 
-# Compute embeddings for the given texts
+# Compute text embeddings
 @st.cache_data
 def compute_embeddings(texts, _model):
     return _model.encode(texts, show_progress_bar=True)
 
-# Perform semantic search using cosine similarity
+# Perform semantic similarity search
 def semantic_search(query, embeddings, model, threshold=0.5):
     query_embedding = model.encode([query])
     sims = cosine_similarity(query_embedding, embeddings)[0]
     return [(i, s) for i, s in enumerate(sims) if s > threshold]
 
-# Generate summary using top-k relevant texts
+# Generate RAG-style summary
 def rag_summarize(texts, summarizer, top_k=5):
     if not texts:
         return "No relevant content to summarize."
@@ -308,7 +308,7 @@ def rag_summarize(texts, summarizer, top_k=5):
     out = summarizer(prompt, max_length=60, min_length=30, do_sample=False)
     return out[0]['summary_text']
 
-# Extract month and year from query
+# Extract month and year from user query
 def extract_month_year(q):
     month_map = {m: i for i, m in enumerate(
         ["january", "february", "march", "april", "may", "june",
@@ -319,7 +319,7 @@ def extract_month_year(q):
     yr = int(ym.group()) if ym else None
     return mon, yr
 
-# Match query against topic-related columns
+# Match user query to bill-related fields
 def extract_topic_match(query, df):
     query_lower = query.lower()
     return df[
@@ -329,32 +329,38 @@ def extract_topic_match(query, df):
         df['policy_impact_areas_standardized'].fillna('').str.lower().str.contains(query_lower)
     ]
 
+# Clean generated summary/insight text
+def clean_summary_text(text):
+    text = re.sub(r"(?i)here are the requested outputs[:\s]*", "", text)
+    text = re.sub(r"(?i)trend summary[:\s]*", "", text)
+    text = re.sub(r"(?i)actionable insight[:\s]*", "", text)
+    return text.strip()
+
 # Streamlit UI setup
 st.set_page_config(page_title="IL Trends Q&A", layout="wide")
-st.title("Illinois Legislative Trends Q&A")
-st.markdown("Ask about trends in topics like education, higher education, funding, etc.")
+st.title("📊 Illinois Legislative Trends Q&A")
+st.markdown("Ask about trends in **topics** like education, higher education, equity, etc.")
 
-# Load data and models
+# Load everything
 df = load_data()
 embed_model, summarizer = load_models()
 
-# User query input
-query = st.text_input(" Ask a question (e.g., ‘trends in Higher education in 2024’):")
+# User question
+query = st.text_input("🔍 Ask a question (e.g., ‘trends in Higher education in 2024’):")
 
 if query:
     mon, yr = extract_month_year(query)
     df2 = extract_topic_match(query, df)
 
     if df2.empty:
-        df2 = df  # fallback if no topic match
-
+        df2 = df
     if yr:
         df2 = df2[df2['status_date'].dt.year == yr]
         if mon:
             df2 = df2[df2['status_date'].dt.month == mon]
-            st.info(f"Filtering by date: **{datetime(yr, mon, 1):%B %Y}**")
+            st.info(f"📅 Filtering by: **{datetime(yr, mon, 1):%B %Y}**")
         else:
-            st.info(f"Filtering by year: **{yr}**")
+            st.info(f"📅 Filtering by year: **{yr}**")
 
     if df2.empty:
         st.warning("No matching records found.")
@@ -366,32 +372,35 @@ if query:
         if not res:
             st.warning("No relevant insights found.")
         else:
-            st.subheader("Top Matching Insights")
+            st.subheader("📘 Top Matching Insights")
             collected = []
 
             for idx, score in sorted(res, key=lambda x: x[1], reverse=True)[:5]:
                 row = df2.iloc[idx]
                 date = row['status_date'].date()
+                bill_number = row['bill_number']
                 cat_std = row['category_&_subcategory_standardized']
                 goal = row['legislative_goal_standardized']
                 intent = row['intent_standardized']
                 stance = row['stance_standardized']
-                trend_summary = row['llama_trend_summary'].strip()
-                bill_number = row['bill_number']
-                url = row['url']
-
-                st.markdown(f"---")
-                st.markdown(f" Date: {date} |  Bill Number: `{bill_number}` | Score: {score:.2f}")
-                st.markdown(f"Category: {cat_std}")
-                st.markdown(f"Goal: {goal}")
-                st.markdown(f"Intent:** {intent} | Stance: {stance}")
-                st.markdown(f"Trend Summary: {trend_summary}")
-                if pd.notna(url) and url.strip():
-                    st.markdown(f"[ View Full Bill Text]({url})")
+                trend_summary = clean_summary_text(row['llama_trend_summary'])
+                insight = clean_summary_text(row['llama_insight'])
+                url = row['full_text_url']
+
+                st.markdown(f"**🗓️ Date:** {date} | **Bill Number:** `{bill_number}` | **Score:** {score:.2f}")
+                st.markdown(f"- **Category:** {cat_std}")
+                st.markdown(f"- **Goal:** {goal}")
+                st.markdown(f"- **Intent:** {intent} | **Stance:** {stance}")
+                st.markdown(f"**🔹 Trend Summary:** {trend_summary}")
+                if insight:
+                    st.markdown(f"**🧠 Actionable Insight:** {insight}")
+                st.markdown(f"[🔗 View Full Bill Text]({url})")
+                st.markdown("---")
 
                 collected.append(row['summary_insight'])
 
-            st.subheader(" RAG-Generated Summary")
+            st.subheader("🧾 RAG-Generated Summary")
             summary = rag_summarize(collected, summarizer)
             st.success(summary)
 
+